Dynamically Jointing character and word embedding for Chinese text Classification.
Xuetao TangXuegang HuPei-Pei LiPublished in: ICKG (2020)
Keyphrases
- text classification
- word segmentation
- n gram
- chinese text
- word recognition
- chinese word segmentation
- text categorization
- chinese characters
- term frequency
- text mining
- unknown words
- training corpus
- language independent
- bag of words
- feature selection
- handwriting recognition
- distributional clustering
- labeled data
- cross lingual
- cursive handwriting
- text documents
- text input
- handwritten words
- data cleaning
- language modeling
- word level
- vector space
- text classifiers
- english text
- sentiment classification
- machine learning
- writing style
- multi label
- sentiment analysis
- data hiding
- printed text
- writing styles
- knn